AI QA Architect: End-to-End LLM Testing & Automation

Arabic.AI; Doha; Vor Ort; QAR 180.000 - 240.000; Vollzeit

Zusammenfassung

Arabic.AI is seeking a Senior QA Engineer to own quality across our AI products, testing LLM-powered features end to end and building automated test and evaluation suites. You will define test strategies for web, API, and backend, evaluate model outputs for accuracy and safety, and drive CI/CD integrated automated UI/API tests.

Collaborating with ML engineers and product managers, you will set acceptance criteria, report defects clearly, and help ensure every release is reliable and safe.

Qualifikationen

• Proven experience testing AI/ML or LLM-based products (chatbots, agents, etc.).
• Hands-on scripting in Python and/or TypeScript/JavaScript.
• Hands-on with UI automation frameworks (Playwright, Cypress, Selenium) and a test framework such as Pytest.
• API testing with Postman, REST Assured, or similar.
• CI/CD and version control: GitHub Actions, GitLab CI or Jenkins; Git.
• Test management: Jira, TestRail, or Zephyr.
• Excellent written English and clear bug reporting.

Aufgaben

• Define test strategies and plans for AI features across web, API, and backend.
• Evaluate model outputs for accuracy, consistency, bias, and safety.
• Build evaluation datasets, including edge cases and adversarial prompts.
• Develop and maintain automated UI, API, and regression tests integrated into CI/CD.
• Run regression testing on model, prompt, and configuration changes.
• Test performance, latency, error handling, and fallback behavior.
• Report defects clearly and provide release-readiness sign-off.
• Test non-deterministic outputs using scoring rubrics and human evaluation.

Kenntnisse

QA automation

Python scripting

TypeScript/JavaScript

Tools

Playwright

Cypress

Selenium

Pytest

Postman

REST Assured

GitHub Actions

GitLab CI

Jenkins

Git

Jira

TestRail

Zephyr

Jobbeschreibung

Arabic.AI is seeking a Senior QA Engineer to own quality across our AI products, testing LLM-powered features end to end and building automated test and evaluation suites. You will define test strategies for web, API, and backend, evaluate model outputs for accuracy and safety, and drive CI/CD integrated automated UI/API tests.

Collaborating with ML engineers and product managers, you will set acceptance criteria, report defects clearly, and help ensure every release is reliable and safe.